计算机与数字工程2025，Vol.53Issue(11)：3168-3173,6.DOI:10.3969/j.issn.1672-9722.2025.11.031
融合改进U-NET和生成对抗网络的对抗防御模型
Adversarial Defence Model With Improved U-NET and Generative Adversarial Network
摘要
Abstract
Aiming at the problems of weak generalization,image denoising and feature extraction of existing countermeasure defense methods,an attack defense model DAU-NET-GAN is proposed,which integrates improved U-NET and generated counter-measure network.By introducing channel attention mechanism and non-local mean filter in U-NET downsampling process,the in-fluence of small perturbations on the image can be reduced as much as possible,the ability of the model is improved to extract the key features of the image,and soft attention mechanism is added to the jump connection part of the generation network,so as to avoid feature redundancy and realize the reconstruction of the adversus-sample.The GCE loss function is used to replace the cross entropy loss function in the training process,which improves the robustness of the model to the opposing samples.The experimental results show that the proposed model can effectively defend against the counter samples generated by various attacks,and the de-fense success rate on MNIST and CIFAR10 data sets can reach 98.96%and 83.88%,which has good general defense effect.关键词
深度神经网络/生成对抗网络/对抗攻击/对抗防御Key words
deep neural network/generative adversarial networks/adversarial attack/adversarial defence分类
信息技术与安全科学引用本文复制引用
莫芮林..融合改进U-NET和生成对抗网络的对抗防御模型[J].计算机与数字工程,2025,53(11):3168-3173,6.基金项目
广州市重点领域研发计划项目(编号:202007010004)资助. （编号:202007010004）
